Big Data Analytics Assignment 1

Q1

First I load the data files

Next I reshape dat into the handful data format. I use tidyr package for the aim instead of reshape package because the foramer is the improved version of the latter.

install.packages('tidyverse')

 URL 'https://cran.rstudio.com/bin/macosx/mavericks/contrib/3.3/tidyverse_1.1.1.tgz' を試しています 
Content type 'application/x-gzip' length 37228 bytes (36 KB)
==================================================
downloaded 36 KB

The downloaded binary packages are in
    /var/folders/1w/nyst5xl16t329h4gpz0j49hm0000gn/T//Rtmp2exVAC/downloaded_packages

library(tidyverse)

Loading tidyverse: ggplot2
Loading tidyverse: tibble
Loading tidyverse: tidyr
Loading tidyverse: readr
Loading tidyverse: purrr
Loading tidyverse: dplyr
Conflicts with tidy packages ----------------------------------------------------------------------------------------------------------------------------------
filter(): dplyr, stats
lag():    dplyr, stats

dat <- dat %>%
tidyr::gather(key=From, value=value, Alabama,Alaska,Arizona,Arkansas,California,Colorado,Connecticut,Delaware,District\ of\ Columbia,Florida,Georgia,Hawaii,Idaho,Illinois,Indiana,Iowa,Kansas,Kentucky,Louisiana,Maine,Maryland,Massachusetts,Michigan,Minnesota,Mississippi,Missouri,Montana,Nebraska,Nevada,New\ Hampshire,New\ Jersey,New\ Mexico,New\ York,North\ Carolina,North\ Dakota,Ohio,Oklahoma,Oregon,Pennsylvania,Rhode\ Island,South\ Carolina,South\ Dakota,Tennessee,Texas,Utah,Vermont,Virginia,Washington,West\ Virginia,Wisconsin,Wyoming)

 エラー:  想定外の入力です  in:
"dat <- dat %>%
tidyr::gather(key=From, value=value, Alabama,Alaska,Arizona,Arkansas,California,Colorado,Connecticut,Delaware,District\"

Delete the puctuations.

Then I add two new columns to the above data frame.

d1 <- merge(dat, states, by.x="From", by.y="States")
d1 <- d1[,c(-5,-6)]
names(d1)[4] <- "ID_From"
d2 <- merge(d1, states, by.x="To", by.y="States")
d2 <- d2[,c(-6,-7)]
names(d2)[5] <- "ID_To"
dat <- d2
dat

Sort the data frame in the ascending order

dat <- arrange(dat, ID_From)
dat <- arrange(dat, ID_To)
dat

Convert the above data frame into the matrix form

Drawing the chord diagram

chorddiag(as.matrix(t5),groupColors=states$Color,showTicks=F,groupnamePadding = 20,groupThickness=.05,groupnameFontsize=10)

row names of the 'data' matrix differ from its column names or the 'groupNames' argument.

Q2

まだindividualを入れてないです。 Read “Stops On Lines” and the all GIS data of bus lines.

library(dplyr)
library(sp)
library(rgdal)
library(leaflet)
library(ggmap)

# Bus Stops
SOL <- readOGR("/Users/susu/Desktop/Hong\ Kong/Semester2/Big_Data/assignment_data/as1/BusStops1216","StopsOnLines1216")
SOL.pj <- spTransform(SOL, CRS("+proj=longlat +datum=WGS84"))

# Bus Routes
CC <- readOGR("/Users/susu/Desktop/Hong\ Kong/Semester2/Big_Data/assignment_data/as1/ComCir1216","ComCir1216")
CC.pj <- spTransform(CC, CRS("+proj=longlat +datum=WGS84"))
LE <- readOGR("/Users/susu/Desktop/Hong\ Kong/Semester2/Big_Data/assignment_data/as1/LimExp1216","LimExp1216")
LE.pj <- spTransform(LE, CRS("+proj=longlat +datum=WGS84"))
LCBD <- readOGR("/Users/susu/Desktop/Hong\ Kong/Semester2/Big_Data/assignment_data/as1/LocalCBD1216","LocalCBD1216")
LCBD.pj <- spTransform(LCBD, CRS("+proj=longlat +datum=WGS84"))
LNCBD <- readOGR("/Users/susu/Desktop/Hong\ Kong/Semester2/Big_Data/assignment_data/as1/LocalNonCBD1216","LocalNonCBD1216")
LNCBD.pj <- spTransform(LNCBD, CRS("+proj=longlat +datum=WGS84"))
RBRT <- readOGR("/Users/susu/Desktop/Hong\ Kong/Semester2/Big_Data/assignment_data/as1/RapidBRT1216","RapidBRT1216")
RBRT.pj <- spTransform(RBRT, CRS("+proj=longlat +datum=WGS84"))

# とりあえずindividual2についてのみreadできることを確認。一旦放置してこれ以外でできるか試す。
I2 <- readOGR("/Users/susu/Desktop/Hong\ Kong/Semester2/Big_Data/assignment_data/as1/Individuals1216","2")
I2.pj <- spTransform(I2, CRS("+proj=longlat +datum=WGS84"))

make Line_list

tmp_CC <- geometry(CC.pj)
tmp_LE <- geometry(LE.pj)
tmp_LCBD <- geometry(LCBD.pj)
tmp_LNCBD <- geometry(LNCBD.pj)
tmp_RBRT <- geometry(RBRT.pj)
tmps <- list(tmp_CC, tmp_LE, tmp_LCBD, tmp_LNCBD, tmp_RBRT)
Line_list <- list()
for (i in 1:5){
  for (j in 1:length(tmps[[i]])){
    Line_list <- c(Line_list, tmps[[i]][j]@lines[[1]]@Lines)
  }
}

make new_id

pjs <- list(CC.pj, LE.pj, LCBD.pj, LNCBD.pj, RBRT.pj)
LinLSs <- list()
for (i in 1:5){
 LinLSs <- c(LinLSs, sapply(pjs[[i]]@lines, function(x) length(x@Lines)))
}
LinLSs <- LinLSs %>% unlist()
new_id <- sapply(1:length(LinLSs), function(x) paste0(x, "_", seq.int(LinLSs[[x]]))) %>% 
  unlist()

SLDF <- mapply(function(x, y) Lines(x, ID = y), x = Line_list, y = new_id) %>%
  list() %>%
  SpatialLines() %>% 
  SpatialLinesDataFrame(data = DAT)

 SpatialLines(.) でエラー: 
  lines list not exclusively filled with Lines objects

make new lines and LA map

Q3

The code is as follows

library(quantmod)
library(highcharter)

x <- getSymbols("AUD/JPY", src = "oanda", auto.assign = FALSE)
y <- getSymbols("GBP/USD", src = "oanda", auto.assign = FALSE)